What is the IQ of gpt-4o?

gpt-4o has an estimated IQ of 85, which ranks #168 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

What is gpt-4o best at?

Among the dimensions with published benchmark results, gpt-4o ranks highest in Reliability (IQ 100, #150 of 177) and Programmatic Reasoning (IQ 96, #152 of 177). Its lowest-ranked measured dimension is Academic Reasoning (IQ 96, #198 of 203).

What is the EQ of gpt-4o?

gpt-4o doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for gpt-4o. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has gpt-4o been tested on?

gpt-4o has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Omniscience, Chess Puzzles, SimpleQA Verified, BullshitBench v2 and CritPt.

How much does gpt-4o cost?

AI IQ doesn't have a verified standard per-token API price for gpt-4o, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.

Is gpt-4o open source?

No — gpt-4o is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed gpt-4o?

gpt-4o was developed by OpenAI, based in the United States.

When was gpt-4o released?

gpt-4o was publicly released on May 13, 2024.

How large is the context window of gpt-4o?

AI IQ hasn't verified an input context limit for gpt-4o from its developer's documentation, so none is listed rather than guessing.

AI IQ doesn't have independent speed measurements for gpt-4o yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.

OpenAIReleased May 13, 2024

Proprietary

gpt-4o

Its best results are in Reliability (#150 of 177) and Programmatic Reasoning (#152 of 177); weakest in Academic Reasoning (#198 of 203). Knowledge Work is estimated, because no results are published yet.

Composite IQ ?

#168 of 176 ranked models · ahead of 5%

OpenAI's #22 model, behind gpt-6.1-sol (141)

Effective cost

Not priced

No standard API rate

Speed

Not measured

No speed data yet

Context

Unverified

Not in publisher docs

Evidence

6of 7 dims

18 of 39 benchmarks

Compare with gpt-6.1-sol

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

MeasuredEstimated95% range

#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10

Abstract ReasoningAbstract

74measured

#185 / 201

3/5

-52.5

Mathematical ReasoningMath

81measured

#168 / 176

3/5

-66

Academic ReasoningAcademic

96measured

#198 / 203

6/6

-39.5

Programmatic ReasoningCoding

96measured

#152 / 177

1/6

-53.5

Computer UseComputer Use

71measured

#166 / 176

1/5

-72

ReliabilityReliability

100measured

#150 / 177

4/6

-34

Knowledge WorkKnowledge Work

79estimated

#171 / 176

0/6

-52.5

gpt-4o95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

18 of 39 Composite IQ benchmarks have a published result for gpt-4o. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 74 · measuredBest: #64 of 76 on Chess Puzzles3/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

13.0%

#64 / 76

Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

0.0%

#65 / 68

Leader gpt-6-astra · 95.0%
Full source leaderboard reconciliation · Oct 23

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

4.5%

#67 / 68

Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Oct 23

Not yet reported

ARC-AGI-3Mystery Game Puzzles

Mathematical Reasoning IQ 81 · measuredBest: #55 of 56 on AIME3/5

BenchmarkScorePercentileRankLeader · source

AIME

11.9%

#55 / 56

Leader gemini-3.1-pro · 98.1%

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

0.4%

#84 / 84

Leader gpt-6-astra · 93.7%
Full source leaderboard reconciliation · Oct 23

MathArena

Full source leaderboard reconciliation · Oct 28

3.4%

#64 / 64

Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 28

Not yet reported

FrontierMath Tier 4ProofBench 1.1

Academic Reasoning IQ 96 · measuredBest: #141 of 159 on CritPt6/6

BenchmarkScorePercentileRankLeader · source

CritPt

Artificial Analysis model leaderboard · Sep 10

0.0%

#141 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis model leaderboard · Sep 10

MMLU-Pro

TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

72.6%

#41 / 45

Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

SciCode

Artificial Analysis model leaderboard · Sep 10

30.9%

#154 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis model leaderboard · Sep 10

MMMU-Pro

Artificial Analysis model leaderboard · Sep 6

56.3%

#84 / 89

Leader fable-5.1 · 90.6%
Artificial Analysis model leaderboard · Sep 6

GPQA Diamond

Artificial Analysis model leaderboard · Sep 10

52.6%

#141 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis model leaderboard · Sep 10

Humanity's Last Exam

Artificial Analysis model leaderboard · Sep 10

2.8%

#165 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis model leaderboard · Sep 10

Programmatic Reasoning IQ 96 · measuredBest: #58 of 61 on LiveCodeBench1/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

43.4%

#58 / 61

Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4

Not yet reported

IOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 71 · measuredBest: #43 of 43 on BrowseComp1/5

BenchmarkScorePercentileRankLeader · source

BrowseComp

LLM Stats BrowseComp · Sep 22

0.6%

#43 / 43

Leader Kimi K3.1 Pro · 92.1%
LLM Stats BrowseComp · Sep 22

Not yet reported

OSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 100 · measuredBest: #93 of 158 on AA Omniscience4/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis model leaderboard · Sep 10

-10.7

#93 / 158

Leader opus-5.5 · 46.4
Artificial Analysis model leaderboard · Sep 10

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

26.0%

#68 / 80

Leader Gemini 4 Argon · 76.0%
Full source leaderboard reconciliation · Oct 23

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

12.0%

#71 / 83

Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23

IFBench

Artificial Analysis model leaderboard · Aug 19

34.3%

#93 / 96

Leader minimax-m3 · 82.9%
Artificial Analysis model leaderboard · Aug 19

Not yet reported

AA Long Context Reasoning v1.1FACTS Grounding

Knowledge Work IQ 79 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 79 shown is estimated from gpt-4o's other dimensions and will be replaced as results come in. How estimates work

AA-Briefcase v1.1GDPval-AA v2.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: May 13, 2024
Developer: OpenAI
Weights: ProprietaryHosted access only

About this score

How much of gpt-4o's IQ is measured, and how the rest is estimated.

18/ 39benchmark results

6/ 7dimensions measured

1estimated

3/5Abstract

3/5Math

6/6Academic

1/6Coding

1/5Computer Use

4/6Reliability

0/6Knowledge Work

Bar height = share of benchmarks with resultsEstimatedNo score

Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Knowledge Work has no published results yet, so its IQ is estimated from gpt-4o's other dimensions. Missing benchmarks can also draw on its predecessor, GPT 4 Turbo; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare gpt-4o

Side-by-side pages for the models it is most often weighed against.

#1 overall

gpt-6.1-sol

IQ141 56 higherEffective cost$6.30

Predecessor

gpt-4-turbo

IQ78 7 lowerEffective cost$50.29

IQ87 2 higherEffective cost$0.088

#2 overall

opus-5.5

IQ141 56 higherEffective cost$35.73

#3 overall

Gemini 4 Argon

IQ140 55 higher

gpt-4oComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about gpt-4o, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →

What is the IQ of gpt-4o?: gpt-4o has an estimated IQ of 85, which ranks #168 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is gpt-4o best at?: Among the dimensions with published benchmark results, gpt-4o ranks highest in Reliability (IQ 100, #150 of 177) and Programmatic Reasoning (IQ 96, #152 of 177). Its lowest-ranked measured dimension is Academic Reasoning (IQ 96, #198 of 203).
What is the EQ of gpt-4o?: gpt-4o doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for gpt-4o. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gpt-4o been tested on?: gpt-4o has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Omniscience, Chess Puzzles, SimpleQA Verified, BullshitBench v2 and CritPt.
How much does gpt-4o cost?: AI IQ doesn't have a verified standard per-token API price for gpt-4o, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
Is gpt-4o open source?: No — gpt-4o is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gpt-4o?: gpt-4o was developed by OpenAI, based in the United States.
When was gpt-4o released?: gpt-4o was publicly released on May 13, 2024.
How large is the context window of gpt-4o?: AI IQ hasn't verified an input context limit for gpt-4o from its developer's documentation, so none is listed rather than guessing.
How fast is gpt-4o?: AI IQ doesn't have independent speed measurements for gpt-4o yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.